INDEX

Explanations

words related to specific ethnic or cultural identities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sar

-0.20

ted

-0.19

ses

-0.19

go

-0.18

shan

-0.17

tt

-0.17

ger

-0.16

gable

-0.16

gie

-0.16

scape

-0.16

POSITIVE LOGITS

apolis

0.31

ism

0.28

alysis

0.28

isme

0.24

thus

0.23

ische

0.22

-American

0.21

omics

0.21

stvo

0.20

ismo

0.20

Activations Density 0.093%

words related to specific ethnic or cultural identities

No Comments

No Known Activations